© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99049
    Prev
    Next
    INDEX
    Explanations

    dates containing 2011

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‘
    -2.11
     —
    -1.97
     …
    -1.87
     '-':
    -1.77
    or
    -1.74
     ‘
    -1.70
    狆
    -1.69
     =
    -1.63
     '+':
    -1.60
    on
    -1.59
    POSITIVE LOGITS
     people
    1.95
    哙
    1.95
     lotes
    1.84
     When
    1.82
    ᯾
    1.81
     zni
    1.77
     jardim
    1.75
     legendary
    1.74
     woman
    1.73
     chilly
    1.73
    Activations Density 0.050%

    No Known Activations